How to find exact matches in propensity score matching using psmatch2

是 否 +2 论坛币

k人 参与回答

经管之家送您一份

应届毕业生专属福利!

求职就业群

赵安豆老师微信：zhaoandou666

经管之家联合CDA

送您一个全额奖学金名额~ !

立即领取

感谢您参与论坛问题回答

经管之家送您两个论坛币！

+2 论坛币

I am using propensity score matching to find matched exporters and non-exporters using psmatch2 in stata (see the stata codes below), and estimate the sales differences between matched exporters and non-exporters.

psmatch2  exporter employees employees2 capital capital2 industry_* year_*, out(sales) common  neighbor(1)

Could someone please let me know how to restrict matched exporter and non-exporter to be in same industry and same year? In other word, I want to match an exporter A with non-exporter B who have smallest propensity score difference and they have to be in same industry and appear in the same year. 多谢指教.

扫码加我 拉你入群

请注明：姓名-公司-职位

以便审核进群资格，未注明则拒绝

分享0 收藏0 回帖

关键词：propensity psmatch2 matching Match score following difference word employees matching

我好久没看人大论坛了，今天看了一下，发现大家都用psmatch2来做matching。这个命令是有问题的，inference是用bootstrap，这在一些情况已经证明是不可行的。
你说的这个不是exact match。如果要设置这两个一致，因为他们是离散的，在nnmatch中选择这些dummy，再设置一下距离的权重，应该可以达到你的目的。但这时是不能用Estimated Propensity Score来matching的，要做方差的调整，我还不知道有没有程序。

How about the way in the following website?

http://www.stata.com/statalist/archive/2010-09/msg00073.html

同问